Wang K, Zuo P, Liu Y, et al. - Researchers sought to create mortality-prediction models for cases with coronavirus disease 2019 (COVID-19). Two hundred ninety six consecutive patients with COVID-19 in the First People’s Hospital of Jiangxia District in Wuhan from January 7, 2020 to February 11, 2020 comprised the training cohort and were assessed for selected baseline clinical and laboratory data through the stepwise Akaike information criterion and ensemble XGBoost model to build mortality-prediction models. Age, history of hypertension and coronary heart disease were included in the clinical model. This model had AUC of 0.88; threshold, -2.6551; sensitivity, 92.31%; specificity, 77.44% and negative predictive value (NPV), 99.34%. Age, high-sensitivity C-reactive protein, peripheral capillary oxygen saturation, neutrophil and lymphocyte count, D-dimer, aspartate aminotransferase and glomerular filtration rate were included in the laboratory model; this model exhibited a significantly stronger discriminatory power than the clinical model, with AUC of 0.98; threshold, -2.998; sensitivity, 100.00%; specificity, 92.82% and NPV, 100.00%. In the subsequent validation cohort (N = 44), clinical model and laboratory model exhibited the AUCs (95% CI) of 0.83 (0.68, 0.93) and 0.88 (0.75, 0.96), respectively.